CS 140: Models of parallel programming: Distributed memory and MPI

Technology Trends: Microprocessor Capacity Moore’s Law: # transistors / chip doubles every 1.5 years Microprocessors keep getting smaller, denser, and more powerful. Gordon Moore (Intel co-founder) predicted in 1965 that the transistor density of semiconductor chips would double roughly every 18 months.

Trends in processor clock speed Triton’s clockspeed is still only 2600 Mhz in 2015!

4-core Intel Sandy Bridge (Triton uses an 8-core version) 2600 Mhz clock speed

Generic Parallel Machine Architecture Key architecture question: Where and how fast are the interconnects? Key algorithm question: Where is the data? Proc Cache L2 Cache L3 Cache Memory Storage Hierarchy Proc Cache L2 Cache L3 Cache Memory Proc Cache L2 Cache L3 Cache Memory potential interconnects

Triton memory hierarchy: I (Chip level) Proc Cache L2 Cache Proc Cache L2 Cache Proc Cache L2 Cache Proc Cache L2 Cache Proc Cache L2 Cache L3 Cache (8MB) Proc Cache L2 Cache Proc Cache L2 Cache Proc Cache L2 Cache (AMD Opteron 8-core Magny-Cours, similar to Triton’s Intel Sandy Bridge) Chip sits in socket, connected to the rest of the node...

Shared Node Memory (64GB) Node L3 Cache (20 MB) P L1/L2 Chip L3 Cache (20 MB) P L1/L2 Chip Triton memory hierarchy II (Node level)

Triton memory hierarchy III (System level) 64GB Node 324 nodes, message-passing communication, no shared memory

Triton memory hierarchy III (System level) Node 324 nodes, message-passing communication, no shared memory 64GB

Some models of parallel computation Computational model Shared memory SPMD / Message passing SIMD / Data parallel PGAS / Partitioned global Loosely coupled Hybrids … Languages Cilk, OpenMP, Pthreads … MPI Cuda, Matlab, OpenCL, … UPC, CAF, Titanium Map/Reduce, Hadoop, … ???

Parallel programming languages Many have been invented – *much* less consensus on what are the best languages than in the sequential world. Could have a whole course on them; we’ll look just a few. Languages you’ll use in homework: C with MPI (very widely used, very old-fashioned) Cilk Plus (a newer upstart) You will choose a language for the final project

Generic Parallel Machine Architecture Key architecture question: Where and how fast are the interconnects? Key algorithm question: Where is the data? Proc Cache L2 Cache L3 Cache Memory Storage Hierarchy Proc Cache L2 Cache L3 Cache Memory Proc Cache L2 Cache L3 Cache Memory potential interconnects

Message-passing programming model Architecture: Each processor has its own memory and cache but cannot directly access another processor’s memory. Language: MPI (“Message-Passing Interface”) A least common denominator based on 1980s technology Links to documentation on course home page SPMD = “Single Program, Multiple Data” interconnect P0 memory NI... P1 memory NI Pn memory NI

Hello, world in MPI #include #include "mpi.h" int main( int argc, char *argv[]) { int rank, size; MPI_Init( &argc, &argv ); MPI_Comm_size( MPI_COMM_WORLD, &size ); MPI_Comm_rank( MPI_COMM_WORLD, &rank ); printf( "Hello world from process %d of %d\n", rank, size ); MPI_Finalize(); return 0; }

MPI in nine routines (all you really need) MPI_InitInitialize MPI_FinalizeFinalize MPI_Comm_sizeHow many processes? MPI_Comm_rankWhich process am I? MPI_WtimeTimer MPI_SendSend data to one proc MPI_RecvReceive data from one proc MPI_BcastBroadcast data to all procs MPI_ReduceCombine data from all procs

Ten more MPI routines (sometimes useful) More collective ops (like Bcast and Reduce): MPI_Alltoall, MPI_Alltoallv MPI_Scatter, MPI_Gather Non-blocking send and receive: MPI_Isend, MPI_Irecv MPI_Wait, MPI_Test, MPI_Probe, MPI_Iprobe Synchronization: MPI_Barrier

Example: Send an integer x from proc 0 to proc 1 MPI_Comm_rank(MPI_COMM_WORLD,&myrank); /* get rank */ int msgtag = 1; if (myrank == 0) { int x = 17; MPI_Send(&x, 1, MPI_INT, 1, msgtag, MPI_COMM_WORLD); } else if (myrank == 1) { int x; MPI_Recv(&x, 1, MPI_INT,0,msgtag,MPI_COMM_WORLD,&status); }

Some MPI Concepts Communicator A set of processes that are allowed to communicate among themselves. Kind of like a “radio channel”. Default communicator: MPI_COMM_WORLD A library can use its own communicator, separated from that of a user program.

Some MPI Concepts Data Type What kind of data is being sent/recvd? Mostly just names for C data types MPI_INT, MPI_CHAR, MPI_DOUBLE, etc.

Some MPI Concepts Message Tag Arbitrary (integer) label for a message Tag of Send must match tag of Recv Useful for error checking & debugging

Parameters of blocking send MPI_Send(buf, count, datatype, dest, tag, comm) Address of Number of items Datatype of Rank of destination Message tag Communicator send buffer to send each item process

Parameters of blocking receive Parameters of blocking receive MPI_Recv(buf, count, datatype, src, tag, comm, status) Address of Maximum number Message tag Communicator receive buffer of items to receive Datatype of each item Rank of source process Status after operation

Example: Send an integer x from proc 0 to proc 1 MPI_Comm_rank(MPI_COMM_WORLD,&myrank); /* get rank */ int msgtag = 1; if (myrank == 0) { int x = 17; MPI_Send(&x, 1, MPI_INT, 1, msgtag, MPI_COMM_WORLD); } else if (myrank == 1) { int x; MPI_Recv(&x, 1, MPI_INT,0,msgtag,MPI_COMM_WORLD,&status); }